A FastMCP server implementation for the Replicate API, providing resource-based access to AI model inference with a focus on image generation.
7 stars1 watching1 forks

MCP Server Replicate

Python Version License Code Style Type Checker Ruff PyPI version

A FastMCP server implementation for the Replicate API, providing resource-based access to AI model inference with a focus on image generation.

Features

  • πŸ–ΌοΈ Resource-based image generation and management
  • πŸ”„ Real-time updates through subscriptions
  • πŸ“ Template-driven parameter configuration
  • πŸ” Comprehensive model discovery and selection
  • πŸͺ Webhook integration for external notifications
  • 🎨 Quality and style presets for optimal results
  • πŸ“Š Progress tracking and status monitoring
  • πŸ”’ Secure API key management

Available Prompts

The server provides several specialized prompts for different tasks:

Text to Image (Primary)

Our most thoroughly tested and robust prompt. Optimized for generating high-quality images from text descriptions with:

  • Detailed style control
  • Quality presets (draft, balanced, quality, extreme)
  • Size and aspect ratio customization
  • Progress tracking and real-time updates

Example:

Create a photorealistic mountain landscape at sunset with snow-capped peaks, quality level: quality, style: photorealistic

Other Prompts

  • Image to Image: Transform existing images (coming soon)
  • Model Selection: Get help choosing the right model for your task
  • Parameter Help: Understand and configure model parameters

Prerequisites

  • Python 3.11 or higher
  • A Replicate API key (get one at https://replicate.com/account)
  • UV for dependency management

Installation

You can install the package directly from PyPI:

# Using UV (recommended)
uv pip install mcp-server-replicate

# Using UVX for isolated environments
uvx install mcp-server-replicate

# Using pip
pip install mcp-server-replicate

Claude Desktop Integration

  1. Make sure you have the latest version of Claude Desktop installed
  2. Open your Claude Desktop configuration:
# macOS
code ~/Library/Application\ Support/Claude/claude_desktop_config.json

# Windows
code %APPDATA%\Claude\claude_desktop_config.json
  1. Add the server configuration using one of these options:
{
  "globalShortcut": "Shift+Alt+A",
  "mcpServers": {
    "replicate": {
      "command": "uv",
      "args": ["tool", "run", "mcp-server-replicate"],
      "env": {
        "REPLICATE_API_TOKEN": "APITOKEN"
      },
      "cwd": "$PATH_TO_REPO"
    }
  }
}
  1. Set your Replicate API key:
# Option 1: Set in your environment
export REPLICATE_API_TOKEN=your_api_key_here

# Option 2: Create a .env file in your home directory
echo "REPLICATE_API_TOKEN=your_api_key_here" > ~/.env
  1. Restart Claude Desktop completely

You should now see the πŸ”¨ icon in Claude Desktop, indicating that the MCP server is available.

Usage

Once connected to Claude Desktop, you can:

  1. Generate images with natural language:

    Create a photorealistic mountain landscape at sunset with snow-capped peaks
    
  2. Browse your generations:

    Show me my recent image generations
    
  3. Search through generations:

    Find my landscape generations
    
  4. Check generation status:

    What's the status of my last generation?
    

Troubleshooting

Server not showing up in Claude Desktop

  1. Check the Claude Desktop logs:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
  1. Verify your configuration:
  • Make sure the path in claude_desktop_config.json is absolute
  • Ensure UV is installed and in your PATH
  • Check that your Replicate API key is set
  1. Try restarting Claude Desktop

For more detailed troubleshooting, see our Debugging Guide.

Documentation

Development

  1. Clone the repository:
git clone https://github.com/gerred/mcp-server-replicate.git
cd mcp-server-replicate
  1. Install development dependencies:
uv pip install --system ".[dev]"
  1. Install pre-commit hooks:
pre-commit install
  1. Run tests:
pytest

Contributing

We welcome contributions! Please see our Contributing Guide for details.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Features

resources
subscriptions
templates
discovery
webhooks
presets
monitoring
security

Category

Integrations